From mboxrd@z Thu Jan 1 00:00:00 1970 From: Florian Weimer Subject: Re: Route cache performance under stress Date: Mon, 26 May 2003 09:18:19 +0200 Sender: linux-net-owner@vger.kernel.org Message-ID: <87adda6uro.fsf@deneb.enyo.de> References: <20030519154852.I39024@shell.cyberus.ca> <20030520011053.GB10419@netnation.com> <20030519.181405.35017608.davem@redhat.com> <20030519212209.P39592@shell.cyberus.ca> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: netdev@oss.sgi.com, linux-net@vger.kernel.org Return-path: To: Jamal Hadi In-Reply-To: <20030519212209.P39592@shell.cyberus.ca> (Jamal Hadi's message of "Mon, 19 May 2003 21:23:08 -0400 (EDT)") List-Id: netdev.vger.kernel.org Jamal Hadi writes: > Also used to attack CISCOs by them kiddies btw. We stand much better > than any CISCO doing caching. Cisco IOS doesn't have this hash collisions problem, they have moved away from hash tables ages ago. You are probably just seeing CPU starvation (Cisco routers aren't equipped with the fastest available CPUs *sigh*, and you lose if routing is not performed by other means). BTW, CEF is just a marketing term. There's a plethora of implementations, ranging from software-only to ASICs to special memory chips (associative arrays with wildcards). These implementations have vastly different implications for router performance. Most notably, CEF is not a cache (not even in the software case), the data structure are changed when updated routing information is encountered and not when packets are received which need to be routed.